Classifier-Guided Latent Diffusion for Small-Molecule Generation
PhD Seminar by: Ali Forooghi
Date: August 13, 2026
Time: 11am -12:30pm
Location: Essex Hall 122
Abstract:
Diffusion models have emerged as a promising class of generative models for molecular design because of their ability to learn complex chemical distributions and support conditional or guided generation. In this work, we investigate a latent diffusion pipeline for property-guided small-molecule generation. The proposed framework represents canonicalized SMILES strings using a frozen ChemBERTa encoder, trains a Transformer-based decoder to reconstruct SELFIES strings from molecular latent embeddings, and learns an unconditional denoising diffusion model in the ChemBERTa latent space. To enable property-directed generation, a differentiable latent property predictor is used to guide the diffusion sampling process. Generated SELFIES strings are converted to SMILES, validated using RDKit, and evaluated using molecular validity, uniqueness, novelty, and predicted property scores. We study guidance toward two drug-relevant binary endpoints: blood--brain barrier permeability and inhibition of human $\beta$-secretase 1. The results suggest that latent diffusion over pretrained molecular embeddings can generate chemically valid and novel molecules while enabling controllable steering toward desired molecular properties.
Keywords: Molecular Generation; Latent Diffusion; Small Molecules;
PhD Doctoral Committee:
External Reader: Dr. Mitra Mirhassani
Internal Reader: Dr. Dan Wu
Internal Reader: Dr. Pooya Moradian Zadeh
Advisor(s): Dr. Alioune Ngom, Dr. Luis Rueda
